© 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. 26536
    Prev
    Next
    INDEX
    Explanations

    trim

    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
     zviri
    -0.08
     desple
    -0.07
     derfor
    -0.07
    ledig
    -0.07
    Snapshot
    -0.07
     тес
    -0.07
     Kib
    -0.07
     statuses
    -0.07
     doi
    -0.07
    _snapshot
    -0.07
    POSITIVE LOGITS
     borders
    0.10
     인정
    0.09
    (edges
    0.09
     Azi
    0.08
     schemes
    0.08
     betr
    0.08
     sche
    0.08
     Borders
    0.08
     accents
    0.08
    ASN
    0.08
    Activations Density 0.016%

    No Known Activations