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. 11878
    Prev
    Next
    INDEX
    Explanations

    body

    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
    _VOL
    -0.08
    .Vol
    -0.08
     Wizard
    -0.08
     yub
    -0.07
     cucumber
    -0.07
    ucumber
    -0.07
    Cab
    -0.07
    Vol
    -0.07
     �
    -0.07
     volatile
    -0.07
    POSITIVE LOGITS
     consolid
    0.08
     konuda
    0.08
     Saat
    0.08
     deden
    0.08
     Mend
    0.08
    Saat
    0.08
     આધ
    0.08
    раз
    0.07
     पर
    0.07
     дәп
    0.07
    Activations Density 0.001%

    No Known Activations