© 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. 91403
    Prev
    Next
    INDEX
    Explanations

    digits

    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
     yari
    -0.09
    レビ
    -0.08
     vlas
    -0.08
     supreme
    -0.08
     begrip
    -0.08
     sjed
    -0.08
    UICollection
    -0.08
     komand
    -0.08
    yum
    -0.08
     Toledo
    -0.08
    POSITIVE LOGITS
     substring
    0.10
    substring
    0.09
    abcdefghijkl
    0.08
     Abbey
    0.08
    .substring
    0.08
    Substring
    0.08
    -aa
    0.08
     Reset
    0.08
    984
    0.08
    aa
    0.08
    Activations Density 0.021%

    No Known Activations