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. 76607
    Prev
    Next
    INDEX
    Explanations

    computer programming

    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
     waterproof
    -0.09
     পদ
    -0.08
     Brick
    -0.08
     пунк
    -0.08
     bás
    -0.08
     Waterproof
    -0.08
     пункт
    -0.07
    aren
    -0.07
    fers
    -0.07
     mfe
    -0.07
    POSITIVE LOGITS
    reject
    0.08
    Reject
    0.08
    toj
    0.08
     DIR
    0.08
    _Work
    0.08
    .scr
    0.07
    API
    0.07
    Work
    0.07
    APT
    0.07
    ães
    0.07
    Activations Density 0.358%

    No Known Activations