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. 60442
    Prev
    Next
    INDEX
    Explanations

    non

    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
    امه
    -0.10
     urrainn
    -0.09
    arande
    -0.09
    աժամ
    -0.08
    ’el
    -0.08
     hag̃
    -0.08
    enem
    -0.08
    amus
    -0.08
     মাধ্যম
    -0.08
     hesum
    -0.08
    POSITIVE LOGITS
    uia
    0.08
    ଡ
    0.07
    ବ
    0.07
    170
    0.07
    bo
    0.07
    ସ
    0.07
    ୍
    0.07
     parity
    0.07
    .poi
    0.07
    0.07
    Activations Density 0.000%

    No Known Activations