© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7987
    Prev
    Next
    INDEX
    Explanations

    image generation prompt format

    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
    926
    -0.08
    IGO
    -0.08
    ²
    -0.07
     frequently
    -0.07
    GY
    -0.07
    ();
↵
↵
    -0.07
    (Math
    -0.07
    CE
    -0.07
    ("""↵
    -0.07
    STM
    -0.07
    POSITIVE LOGITS
     commas
    0.14
     comma
    0.13
    comma
    0.11
    Comma
    0.10
    ijven
    0.09
    เล
    0.09
    acijos
    0.08
     Separator
    0.08
     quotations
    0.08
     compartments
    0.08
    Activations Density 0.009%

    No Known Activations