© 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. 50928
    Prev
    Next
    INDEX
    Explanations

    assistant

    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
    (vals
    -0.10
    ,a
    -0.10
    ,A
    -0.10
    (u
    -0.10
    (ax
    -0.10
    ,'.
    -0.10
    (attr
    -0.10
    (meta
    -0.10
    ,Q
    -0.10
    (am
    -0.10
    POSITIVE LOGITS
     endli
    0.14
    %timeout
    0.13
     日日
    0.12
     qvod
    0.12
    定位胆
    0.12
    久久久
    0.12
     dydd
    0.11
    毛片
    0.11
     多宝
    0.11
     vracht
    0.11
    Activations Density 0.016%

    No Known Activations