© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 99272
    Prev
    Next
    INDEX
    Explanations

    乎

    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
     roaming
    -0.09
     прич
    -0.08
     briefly
    -0.08
    DM
    -0.07
     somehow
    -0.07
    bindings
    -0.07
     loosely
    -0.07
    uttering
    -0.07
    Ave
    -0.07
     invés
    -0.07
    POSITIVE LOGITS
     negligible
    0.11
     כמעט
    0.09
     거의
    0.09
     limitless
    0.09
    .pin
    0.08
     तरह
    0.08
     almost
    0.08
     prácticamente
    0.08
     kaum
    0.08
     Pinot
    0.08
    Activations Density 0.018%

    No Known Activations