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. 56103
    Prev
    Next
    INDEX
    Explanations

    ulation

    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
     Bay
    -0.09
    hadow
    -0.08
     comparing
    -0.08
     DP
    -0.08
     이해
    -0.07
    -0.07
     babae
    -0.07
     Segment
    -0.07
     statement
    -0.07
    erweise
    -0.07
    POSITIVE LOGITS
     ót
    0.09
     মো
    0.08
    じ
    0.08
    ália
    0.08
    モ
    0.08
    Launching
    0.08
    uina
    0.08
    Toute
    0.08
     interruptions
    0.07
     moeilijk
    0.07
    Activations Density 0.001%

    No Known Activations