© 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. 51321
    Prev
    Next
    INDEX
    Explanations

    conf

    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
    ර්
    -0.09
     váll
    -0.09
    Protected
    -0.09
     iš
    -0.08
    protected
    -0.08
     Protected
    -0.08
    anément
    -0.08
     antagonist
    -0.08
    ánea
    -0.08
    aría
    -0.08
    POSITIVE LOGITS
    etti
    0.18
    issões
    0.11
    ett
    0.11
    essions
    0.10
    eti
    0.10
    itures
    0.09
    itm
    0.09
    itiv
    0.09
    ected
    0.09
    icts
    0.09
    Activations Density 0.001%

    No Known Activations