© 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. 24801
    Prev
    Next
    INDEX
    Explanations

    Prepositions/articles

    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
    edit
    -0.09
    ietf
    -0.08
     scrapbook
    -0.07
     ļ
    -0.07
    unaan
    -0.07
    expand
    -0.07
    itul
    -0.07
    Prayer
    -0.07
    _constructor
    -0.07
    Mint
    -0.07
    POSITIVE LOGITS
     dä
    0.08
     nagyon
    0.08
     lige
    0.08
     divisible
    0.08
    -AS
    0.08
    _TERM
    0.07
    .AD
    0.07
     quarters
    0.07
     Comparable
    0.07
    -IN
    0.07
    Activations Density 0.433%

    No Known Activations