© 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. 8048
    Prev
    Next
    INDEX
    Explanations

    generating lists

    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
    The
    -0.08
     '
    -0.08
     Leia
    -0.08
     The
    -0.08
    Story
    -0.07
    Hung
    -0.07
    Jane
    -0.07
    Office
    -0.07
     Jews
    -0.07
    Unmount
    -0.07
    POSITIVE LOGITS
     repetition
    0.15
     repetitive
    0.14
     repetitions
    0.14
     répét
    0.13
    .repeat
    0.13
     repeat
    0.13
     repetir
    0.13
     repeats
    0.13
     repet
    0.13
     반복
    0.13
    Activations Density 0.051%

    No Known Activations