© 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. 23-RESID-POST-AA
    11. 48708
    Prev
    Next
    INDEX
    Explanations

    say "quet" or "ques"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     knot
    -0.08
    bha
    -0.08
     mf
    -0.08
     EA
    -0.08
     bona
    -0.08
    521
    -0.07
     AU
    -0.07
     BN
    -0.07
    vera
    -0.07
     inquire
    -0.07
    POSITIVE LOGITS
    무료
    0.09
     무료
    0.09
     fällt
    0.09
     julg
    0.09
     masterm
    0.09
    লো
    0.08
    .loading
    0.08
     impressions
    0.08
    .preprocessing
    0.08
    রিক
    0.08
    Activations Density 0.000%

    No Known Activations