© 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. 19-RESID-POST-AA
    11. 102823
    Prev
    Next
    INDEX
    Explanations

    power

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilian
    -0.08
     मिनट
    -0.08
    Appear
    -0.08
     froze
    -0.08
     Minuten
    -0.08
     Energy
    -0.08
     modelos
    -0.08
     aired
    -0.07
     Fired
    -0.07
    <Comment
    -0.07
    POSITIVE LOGITS
     supplies
    0.16
     supply
    0.16
     공급
    0.14
    train
    0.14
    source
    0.14
    _supply
    0.14
    versorgung
    0.14
    供应
    0.13
     Supplies
    0.12
    -source
    0.12
    Activations Density 0.008%

    No Known Activations