© 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. 18481
    Prev
    Next
    INDEX
    Explanations

    key, specific

    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
    ;
    -0.13
    —we
    -0.13
    ,
    -0.13
    ,we
    -0.12
    ,//
    -0.12
     (**
    -0.11
    —a
    -0.11
    ,—
    -0.11
    ،
    -0.11
    某
    -0.11
    POSITIVE LOGITS
     notable
    0.14
     relevant
    0.13
    具体
    0.13
     aspects
    0.12
     specific
    0.12
     prominent
    0.11
     key
    0.11
     possible
    0.11
     technical
    0.11
     illustrative
    0.11
    Activations Density 0.053%

    No Known Activations