© 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. 26399
    Prev
    Next
    INDEX
    Explanations

    Combinatorics calculations

    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
     intimate
    -0.07
     incor
    -0.07
     schl
    -0.07
    ggy
    -0.07
     slogan
    -0.07
     partner
    -0.07
    案
    -0.07
     Appalachian
    -0.07
    gg
    -0.07
     mood
    -0.07
    POSITIVE LOGITS
    .RO
    0.08
    _RA
    0.07
     totalmente
    0.07
     stipend
    0.07
    emeen
    0.07
    *sizeof
    0.07
     pesc
    0.07
     Derm
    0.07
     Cute
    0.07
    以内
    0.07
    Activations Density 0.013%

    No Known Activations