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. 12827
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
    (http
    -0.08
    וון
    -0.08
    Speech
    -0.07
    кту
    -0.07
    уч
    -0.07
    వి
    -0.07
    -0.07
    (((
    -0.07
     approximate
    -0.07
    enteri
    -0.07
    POSITIVE LOGITS
     NUM
    0.08
     vidéos
    0.08
     Chang
    0.07
    NUM
    0.07
    nar
    0.07
     Euler
    0.07
    0.07
     Portsmouth
    0.07
     scrambled
    0.07
     matérias
    0.07
    Activations Density 0.000%

    No Known Activations