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. 109495
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
    .Push
    -0.08
     Burl
    -0.08
     images
    -0.08
    _Sub
    -0.07
    itto
    -0.07
     pivotal
    -0.07
     Sø
    -0.07
     DSC
    -0.07
    (Contact
    -0.07
     BUR
    -0.07
    POSITIVE LOGITS
     realizou
    0.09
    Wann
    0.08
    kam
    0.08
     roh
    0.08
     gagner
    0.08
    iniz
    0.08
     অধিক
    0.08
     accomplishment
    0.08
     conceive
    0.08
    Hil
    0.07
    Activations Density 0.008%

    No Known Activations