© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18611
    Prev
    Next
    INDEX
    Explanations

    exclusivity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     valid
    -0.08
     available
    -0.08
     ઉપલબ્ધ
    -0.08
     viable
    -0.08
    Available
    -0.08
    available
    -0.08
     compatible
    -0.08
     disponible
    -0.08
     Compatible
    -0.08
     pool
    -0.07
    POSITIVE LOGITS
     exclus
    0.19
     Exclus
    0.17
     uniqueness
    0.17
     exclusivo
    0.16
     exclusively
    0.15
     exclusivos
    0.14
     exklus
    0.14
     exclusiva
    0.14
     uitsluitend
    0.13
     ONLY
    0.13
    Activations Density 0.032%

    No Known Activations