© 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. 91297
    Prev
    Next
    INDEX
    Explanations

    still

    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
    _Project
    -0.08
     Johnson
    -0.07
     sorpresa
    -0.07
    _No
    -0.07
    aption
    -0.07
     серв
    -0.07
     njen
    -0.07
    erv
    -0.07
    .Language
    -0.07
    ollapse
    -0.07
    POSITIVE LOGITS
     thereof
    0.09
     Paula
    0.08
    /current
    0.08
    ु�
    0.07
     też
    0.07
     STYLE
    0.07
    २०
    0.07
    ish
    0.07
     itd
    0.07
     defaultdict
    0.07
    Activations Density 0.057%

    No Known Activations