© 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. 103003
    Prev
    Next
    INDEX
    Explanations

    dialogue scenes

    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
     not
    -0.10
     не
    -0.09
     slightly
    -0.08
    /A
    -0.08
    obar
    -0.08
    ा
    -0.07
    n't
    -0.07
    ить
    -0.07
    uon
    -0.07
    Understanding
    -0.07
    POSITIVE LOGITS
     ajustes
    0.11
     ajuste
    0.09
    _jsii
    0.09
    调整
    0.09
     breyting
    0.09
     Ajust
    0.09
     ajustar
    0.08
     hookup
    0.08
     adjustments
    0.08
     gewöhn
    0.08
    Activations Density 0.001%

    No Known Activations