© 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. 7-RESID-POST-AA
    11. 1291
    Prev
    Next
    INDEX
    Explanations

    statistics/probability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _RELEASE
    -0.08
     RELEASE
    -0.07
    кость
    -0.07
     antar
    -0.07
     जारी
    -0.07
     releases
    -0.07
    Styl
    -0.07
     Daim
    -0.07
    _Control
    -0.07
     frente
    -0.06
    POSITIVE LOGITS
     ملا
    0.09
     casin
    0.08
    Coment
    0.08
    YNAM
    0.08
    踏
    0.08
     cocktail
    0.08
    witter
    0.08
     manure
    0.08
     sociais
    0.08
    AVG
    0.08
    Activations Density 0.002%

    No Known Activations