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. 112184
    Prev
    Next
    INDEX
    Explanations

    code

    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
    !↵↵
    -0.07
     GAL
    -0.07
     why
    -0.07
     popular
    -0.07
    -0.07
    !
    -0.07
     tailles
    -0.07
     populaire
    -0.07
     maatschapp
    -0.07
    เทศ
    -0.07
    POSITIVE LOGITS
     لیا
    0.08
     juli
    0.08
    legging
    0.08
     Água
    0.08
    éo
    0.08
     baino
    0.08
    czaj
    0.08
     Finale
    0.08
    ẹẹrẹ
    0.08
    IDEO
    0.08
    Activations Density 0.001%

    No Known Activations