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. 65752
    Prev
    Next
    INDEX
    Explanations

    Conversational responses

    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
     Sweep
    -0.08
    ameda
    -0.07
    选
    -0.07
    .nano
    -0.07
     Javier
    -0.07
    <com
    -0.07
     Mobility
    -0.07
     usability
    -0.07
    arlow
    -0.07
    _fact
    -0.07
    POSITIVE LOGITS
     basil
    0.08
     hopefully
    0.08
    rema
    0.08
     reflector
    0.07
     inklusive
    0.07
     rentrer
    0.07
     Dra
    0.07
    ско
    0.07
     drankje
    0.07
     erkl
    0.07
    Activations Density 0.159%

    No Known Activations