© 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. 78838
    Prev
    Next
    INDEX
    Explanations

    saw

    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
    [,]
    -0.09
    ...
    -0.08
    Reduced
    -0.08
     craftsmanship
    -0.08
    research
    -0.07
    ()
    -0.07
    Some
    -0.07
    Research
    -0.07
    Company
    -0.07
    ZZ
    -0.07
    POSITIVE LOGITS
     Emi
    0.09
     Beethoven
    0.08
    īk
    0.08
     Oreo
    0.08
    只有
    0.08
     उपाय
    0.07
     Escape
    0.07
    uneq
    0.07
     Imp
    0.07
     DCHECK
    0.07
    Activations Density 0.015%

    No Known Activations