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. 11642
    Prev
    Next
    INDEX
    Explanations

    wrapper

    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
    พันธ์
    -0.09
    Nas
    -0.09
     мындай
    -0.08
    [offset
    -0.08
     nesse
    -0.08
     nominal
    -0.08
     nas
    -0.08
     alumnado
    -0.08
    കാര
    -0.08
     oldest
    -0.08
    POSITIVE LOGITS
     rou
    0.07
     Scope
    0.07
    _Request
    0.07
     Translator
    0.07
    拓
    0.06
     उपाय
    0.06
    ></
    0.06
     더욱
    0.06
     Bertrand
    0.06
    ilter
    0.06
    Activations Density 0.001%

    No Known Activations