Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 112021
    Prev
    Next
    INDEX
    Explanations

    ^{-

    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
    Conte
    -0.08
     зов
    -0.07
     soft
    -0.07
     VIP
    -0.07
    Soft
    -0.07
    Oval
    -0.07
    VILLE
    -0.07
     PERF
    -0.07
     Oval
    -0.06
     અક
    -0.06
    POSITIVE LOGITS
     fırs
    0.09
     rokov
    0.08
    -il
    0.08
     délais
    0.08
    জ্জ
    0.08
    libft
    0.08
    datetime
    0.08
     další
    0.08
    елер
    0.08
     decade
    0.08
    Activations Density 0.005%

    No Known Activations