© 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. 103124
    Prev
    Next
    INDEX
    Explanations

    code

    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
    afanya
    -0.08
    ام
    -0.08
    arsuaq
    -0.08
    ämä
    -0.08
    ات
    -0.08
    annaq
    -0.08
    ATIVE
    -0.08
    ukua
    -0.08
    AMENTO
    -0.08
    aliwa
    -0.08
    POSITIVE LOGITS
    pendency
    0.17
    pendent
    0.15
    forces
    0.15
    _review
    0.15
    behind
    0.14
    velopment
    0.14
    pendencies
    0.14
    gen
    0.14
     리뷰
    0.14
    cs
    0.14
    Activations Density 0.019%

    No Known Activations