© 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. 102923
    Prev
    Next
    INDEX
    Explanations

    boot

    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
    ’autre
    -0.09
    IONES
    -0.08
     autre
    -0.08
    ої
    -0.08
    'autre
    -0.08
    회를
    -0.08
    eyay
    -0.08
     ficha
    -0.08
     fich
    -0.07
     approfond
    -0.07
    POSITIVE LOGITS
    str
    0.18
    strap
    0.17
     strap
    0.15
    per
    0.15
    rapped
    0.15
     strapped
    0.14
     bootstrap
    0.14
     Strap
    0.13
    legging
    0.13
    /bootstrap
    0.13
    Activations Density 0.006%

    No Known Activations