© 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. 94988
    Prev
    Next
    INDEX
    Explanations

    self-help

    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
    .mean
    -0.08
    ipal
    -0.08
    .margin
    -0.07
     films
    -0.07
     tensions
    -0.07
     білді
    -0.07
     заключ
    -0.07
     σκο
    -0.07
     exceptional
    -0.07
     жай
    -0.07
    POSITIVE LOGITS
     Experts
    0.08
     Humans
    0.08
    不可
    0.08
     Interviews
    0.08
     einzigartige
    0.08
    :::
    0.08
    Unique
    0.08
     Coronavirus
    0.08
     bize
    0.08
    Owners
    0.08
    Activations Density 0.025%

    No Known Activations