© 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. 47229
    Prev
    Next
    INDEX
    Explanations

    are

    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
     বৃ
    -0.07
    -enabled
    -0.07
     참석
    -0.07
     العض
    -0.07
     sobrem
    -0.07
     overtime
    -0.07
     Configuration
    -0.07
    auw
    -0.07
    .Query
    -0.07
     Municipality
    -0.07
    POSITIVE LOGITS
    Delhi
    0.08
    eft
    0.08
    plet
    0.08
     gravid
    0.08
     éclair
    0.08
     piz
    0.07
    915
    0.07
    cohol
    0.07
     düny
    0.07
     Illumin
    0.07
    Activations Density 0.000%

    No Known Activations