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. 43230
    Prev
    Next
    INDEX
    Explanations

    mathematical/geometric proofs

    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
     학
    -0.08
    _learning
    -0.07
     onto
    -0.07
    张
    -0.07
    就是
    -0.07
     ''.
    -0.07
    ,每
    -0.07
     Jan
    -0.07
    .title
    -0.07
     gone
    -0.07
    POSITIVE LOGITS
     numerator
    0.10
     ചെയ്തു
    0.09
     denominator
    0.09
     coer
    0.09
     igualmente
    0.09
     coher
    0.08
     באופן
    0.08
     sweetest
    0.08
     divisor
    0.08
     সাজ
    0.08
    Activations Density 0.019%

    No Known Activations