© 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. 3-RESID-POST-AA
    11. 12860
    Prev
    Next
    INDEX
    Explanations

    extends

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lex
    -0.09
     mux
    -0.08
     Stat
    -0.08
     Lex
    -0.08
    lex
    -0.08
    LEX
    -0.07
     persone
    -0.07
     soothing
    -0.07
     exerce
    -0.07
     músico
    -0.07
    POSITIVE LOGITS
     disturbance
    0.08
     reun
    0.08
    Jvm
    0.07
    ફ
    0.07
    ्झ
    0.07
     rearr
    0.07
     compris
    0.07
    ులను
    0.07
     disturbances
    0.06
     réun
    0.06
    Activations Density 0.000%

    No Known Activations