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. 55886
    Prev
    Next
    INDEX
    Explanations

    Do

    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
    袋
    -0.07
     caros
    -0.07
     cạnh
    -0.07
    公平
    -0.07
     berd
    -0.07
    scores
    -0.07
     plain
    -0.07
    шись
    -0.07
     adolesc
    -0.07
     Scores
    -0.07
    POSITIVE LOGITS
     spoof
    0.09
    IRS
    0.08
     infestation
    0.08
    프
    0.08
    _auth
    0.08
    (fake
    0.08
    SAR
    0.08
    発送
    0.07
     ಎಂದ
    0.07
    �
    0.07
    Activations Density 0.002%

    No Known Activations