© 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. 11-RESID-POST-AA
    11. 7948
    Prev
    Next
    INDEX
    Explanations

    thresholds, limits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Trata
    -0.08
     Erasmus
    -0.08
    ecos
    -0.08
    ματα
    -0.08
    Dam
    -0.08
     Noah
    -0.07
     mosquito
    -0.07
     näher
    -0.07
    _setopt
    -0.07
    kua
    -0.07
    POSITIVE LOGITS
    ，然后
    0.08
     అనే
    0.08
     ஆகிய
    0.08
     అని
    0.08
    。また
    0.08
     అన్న
    0.07
    vd
    0.07
     ڏ
    0.07
    性生活
    0.07
    -div
    0.07
    Activations Density 0.015%

    No Known Activations