© 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. 3-RESID-POST-AA
    11. 12792
    Prev
    Next
    INDEX
    Explanations

    از

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _flash
    -0.08
    mouseup
    -0.08
    Quand
    -0.08
    στη
    -0.08
     syndic
    -0.07
     socialist
    -0.07
    geist
    -0.07
    mei
    -0.07
    uels
    -0.07
    .'"
    -0.07
    POSITIVE LOGITS
     Ethiopia
    0.08
    hort
    0.08
     Ethiopian
    0.07
     Deg
    0.07
    Deg
    0.07
    ehr
    0.07
     technically
    0.07
    ${
    0.07
     مسؤول
    0.07
     direcion
    0.07
    Activations Density 0.000%

    No Known Activations