© 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. 99126
    Prev
    Next
    INDEX
    Explanations

    automata theory

    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
    す
    -0.09
     (%)
    -0.09
    また
    -0.08
     matem
    -0.08
    _percentage
    -0.08
     swinger
    -0.07
     massively
    -0.07
     mathematical
    -0.07
     län
    -0.07
     trium
    -0.07
    POSITIVE LOGITS
     distinguish
    0.10
     विभ
    0.09
     distinguishing
    0.09
     differentiate
    0.09
     indist
    0.09
     પાડ
    0.08
     Unterschiede
    0.08
     айыр
    0.08
     분
    0.08
     Besch
    0.08
    Activations Density 0.002%

    No Known Activations