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. 119194
    Prev
    Next
    INDEX
    Explanations

    -

    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
     zá
    -0.08
     חל
    -0.08
    .Substring
    -0.08
     Harden
    -0.07
     brag
    -0.07
    /interface
    -0.07
     evapor
    -0.07
     ув
    -0.07
     스타일
    -0.07
    .stdout
    -0.07
    POSITIVE LOGITS
    dua
    0.08
     polis
    0.08
     notices
    0.08
     verbose
    0.08
    verbose
    0.07
    xx
    0.07
    seq
    0.07
    ņ
    0.07
    ██
    0.07
    ata
    0.07
    Activations Density 0.028%

    No Known Activations