© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 68116
    Prev
    Next
    INDEX
    Explanations

    code

    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
    raad
    -0.07
     بو
    -0.07
    MVC
    -0.07
    BW
    -0.07
     nxt
    -0.07
     לכך
    -0.07
    INARY
    -0.07
    ielt
    -0.07
    MQ
    -0.07
    >");↵
    -0.07
    POSITIVE LOGITS
     cadáver
    0.08
     tive
    0.08
     John's
    0.08
     tendría
    0.07
    _De
    0.07
    larının
    0.07
    acağı
    0.07
     Byzant
    0.07
    野
    0.07
    utely
    0.07
    Activations Density 0.000%

    No Known Activations