© 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. 23-RESID-POST-AA
    11. 51207
    Prev
    Next
    INDEX
    Explanations

    say ako

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     துண
    -0.08
     tort
    -0.08
     ફ
    -0.07
     સમય
    -0.07
    sub
    -0.07
    ưng
    -0.07
    -0.07
    YC
    -0.07
    ory
    -0.07
    ุม
    -0.07
    POSITIVE LOGITS
    ako
    0.10
    akoa
    0.09
    Logical
    0.08
     batera
    0.08
     carbonation
    0.08
    oota
    0.08
    ereza
    0.07
    ко
    0.07
     Housewives
    0.07
     akoz
    0.07
    Activations Density 0.000%
    No Known Activations