© 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. 75544
    Prev
    Next
    INDEX
    Explanations

    options

    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
    Indoor
    -0.09
     Fü
    -0.09
     Olim
    -0.08
    ||↵
    -0.08
    Kala
    -0.08
    �
    -0.08
    CHF
    -0.08
    cv
    -0.07
     spare
    -0.07
     Teile
    -0.07
    POSITIVE LOGITS
    -mentioned
    0.10
     outlined
    0.09
    -listed
    0.09
     criteria
    0.09
    .spi
    0.08
     criter
    0.08
     wọnyi
    0.08
     criterion
    0.08
     гал
    0.08
     todos
    0.08
    Activations Density 0.020%

    No Known Activations