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. 48447
    Prev
    Next
    INDEX
    Explanations

    [

    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
     approximation
    -0.08
    isable
    -0.08
    559
    -0.08
    _checksum
    -0.08
     mers
    -0.07
     maslahat
    -0.07
     underestimate
    -0.07
    560
    -0.07
     танд
    -0.07
     UK's
    -0.07
    POSITIVE LOGITS
    =utf
    0.08
     活
    0.07
     =================================================================
    0.07
    娇
    0.07
    requirements
    0.07
     querendo
    0.07
    符
    0.07
    bounce
    0.07
     requiere
    0.07
     activate
    0.07
    Activations Density 0.004%

    No Known Activations