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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 61174
    Prev
    Next
    INDEX
    Explanations

    folding

    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
    pas
    -0.09
     we'd
    -0.08
    subst
    -0.08
     pasión
    -0.08
     barr
    -0.08
     delin
    -0.08
     menop
    -0.08
     Pas
    -0.07
     carcin
    -0.07
     intoxic
    -0.07
    POSITIVE LOGITS
     folds
    0.09
     folded
    0.09
     व्यव
    0.09
     김
    0.09
    .wrap
    0.08
     rectangle
    0.08
     fold
    0.08
     chinos
    0.08
     supervised
    0.07
     Compress
    0.07
    Activations Density 0.008%

    No Known Activations