Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 88045
    Prev
    Next
    INDEX
    Explanations

    Increase, folds

    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
    Vue
    -0.08
    adou
    -0.08
     reign
    -0.08
     vun
    -0.07
    Soft
    -0.07
     seguros
    -0.07
    incident
    -0.07
     abuse
    -0.07
    -0.07
    attribute
    -0.07
    POSITIVE LOGITS
     Travers
    0.08
     traverse
    0.08
    بع
    0.08
     входят
    0.08
     идут
    0.07
     Ode
    0.07
     produziert
    0.07
    Traverse
    0.07
     entero
    0.07
     Welding
    0.07
    Activations Density 0.000%

    No Known Activations