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. 77154
    Prev
    Next
    INDEX
    Explanations

    articles

    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
     inlet
    -0.08
    ค่า
    -0.07
     موږ
    -0.07
     servo
    -0.07
     ماده
    -0.07
     aperture
    -0.07
     parameter
    -0.07
     constant
    -0.07
     poles
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    Genre
    0.08
    imbus
    0.08
     Genre
    0.08
    Weekend
    0.08
    iculture
    0.08
     Gan
    0.08
    _master
    0.08
     Blood
    0.08
     Bibli
    0.08
     Garrett
    0.08
    Activations Density 0.080%

    No Known Activations