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. 111418
    Prev
    Next
    INDEX
    Explanations

    forward-looking statements

    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
    448
    -0.10
    ız
    -0.09
    .pixel
    -0.09
    .rating
    -0.08
    _pixel
    -0.08
    Pixel
    -0.08
    _PIX
    -0.08
     Curtis
    -0.08
     """↵↵
    -0.08
     покры
    -0.08
    POSITIVE LOGITS
    unsafe
    0.09
     risky
    0.09
     foregoing
    0.08
    plek
    0.08
    boolean
    0.08
    trigger
    0.08
    ?,?,?,?,
    0.08
     LTD
    0.08
     emis
    0.08
    dynamic
    0.08
    Activations Density 0.008%

    No Known Activations