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. 12077
    Prev
    Next
    INDEX
    Explanations

    max

    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
     overhead
    -0.08
     innocent
    -0.07
    rec
    -0.07
    Rec
    -0.07
    weights
    -0.07
    REC
    -0.07
    peer
    -0.07
     rec
    -0.07
    $obj
    -0.07
     prohibits
    -0.07
    POSITIVE LOGITS
    贡
    0.08
     kayaking
    0.08
    涯
    0.08
     фильм
    0.08
     alın
    0.08
     Garmin
    0.07
    etrics
    0.07
     farið
    0.07
     pedals
    0.07
     Gris
    0.07
    Activations Density 0.001%

    No Known Activations