© 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. 48165
    Prev
    Next
    INDEX
    Explanations

    say "the ending ."

    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
     vinte
    -0.08
     thre
    -0.08
     трех
    -0.08
    解绑
    -0.08
    473
    -0.08
     Beng
    -0.08
     "../../
    -0.08
    500
    -0.08
     *_
    -0.08
     biyu
    -0.07
    POSITIVE LOGITS
    .a
    0.18
    (a
    0.18
    .A
    0.16
    -a
    0.16
    a
    0.15
    -A
    0.14
    A
    0.14
    ‑
    0.14
    (A
    0.13
    +a
    0.13
    Activations Density 0.013%

    No Known Activations