© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29758
    Prev
    Next
    INDEX
    Explanations

    ziehungs

    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
     eru
    -0.10
     երեխ
    -0.08
    rịta
    -0.08
     մանկ
    -0.08
     աշ
    -0.08
     մարդու
    -0.08
     noodles
    -0.08
     ներկայացուցիչ
    -0.08
    րույց
    -0.08
    ื้อ
    -0.08
    POSITIVE LOGITS
     LICENSE
    0.08
     lag
    0.07
    vap
    0.07
     laser
    0.07
     hammer
    0.07
     finn
    0.07
    _frames
    0.07
    fv
    0.07
     fscanf
    0.07
     ور
    0.07
    Activations Density 0.000%

    No Known Activations