Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 45352
    Prev
    Next
    INDEX
    Explanations

    6

    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
     Trem
    -0.08
     Daniela
    -0.08
     Whiskey
    -0.08
    /dr
    -0.08
    &r
    -0.08
    Dr
    -0.08
    -0.07
     Ethan
    -0.07
    adis
    -0.07
    <W
    -0.07
    POSITIVE LOGITS
     ruled
    0.08
    929
    0.08
    宋
    0.07
    入住
    0.07
     fiss
    0.07
     fuera
    0.07
    .keras
    0.07
     keras
    0.07
    住
    0.07
    ರ್ಶ
    0.07
    Activations Density 0.000%

    No Known Activations