© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 112361
    Prev
    Next
    INDEX
    Explanations

    Science

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     skladu
    -0.08
    х
    -0.07
     있습니다
    -0.07
     уп
    -0.07
     prend
    -0.07
     dovol
    -0.07
    �
    -0.07
    xff
    -0.07
    _destination
    -0.07
     있다는
    -0.07
    POSITIVE LOGITS
     nid
    0.09
     firef
    0.08
    Dungeon
    0.08
     जारी
    0.08
     jogo
    0.08
     rua
    0.08
     અગ
    0.08
    (pc
    0.08
     Everest
    0.08
     ardh
    0.08
    Activations Density 0.004%

    No Known Activations