© 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. 47918
    Prev
    Next
    INDEX
    Explanations

    code snippets (early exit)

    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
    nier
    -0.08
    数
    -0.08
     number
    -0.08
    zahl
    -0.08
     and
    -0.08
     Each
    -0.07
     nature
    -0.07
     seat
    -0.07
    fant
    -0.07
    _faces
    -0.07
    POSITIVE LOGITS
     предотвращ
    0.11
     먼저
    0.11
    Early
    0.11
    .Skip
    0.11
     prematurely
    0.11
     premature
    0.10
     제외
    0.10
    .skip
    0.10
     Early
    0.10
    Skipping
    0.10
    Activations Density 0.013%

    No Known Activations