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. 12771
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations

    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
     adqu
    -0.07
    كن
    -0.07
     conserver
    -0.07
     vera
    -0.07
     verdadeiro
    -0.07
     designate
    -0.07
    كت
    -0.07
     united
    -0.07
     nou
    -0.07
    Combine
    -0.07
    POSITIVE LOGITS
    _FULLSCREEN
    0.09
     тк
    0.08
     Lucky
    0.08
     Glück
    0.08
     Weiß
    0.08
     행복
    0.08
     convention
    0.07
     Wei
    0.07
     hurried
    0.07
    _FORE
    0.07
    Activations Density 0.070%

    No Known Activations