© 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. 65331
    Prev
    Next
    INDEX
    Explanations

    for

    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
     (
    -0.09
    I
    -0.08
    Words
    -0.08
    K
    -0.08
     \(
    -0.08
    sem
    -0.08
    Ren
    -0.07
    Sem
    -0.07
    agse
    -0.07
     vs
    -0.07
    POSITIVE LOGITS
     Demo
    0.09
     Français
    0.08
    965
    0.08
     réunion
    0.08
     prende
    0.08
     envia
    0.07
     dentre
    0.07
     pulver
    0.07
     �
    0.07
     Hamburger
    0.07
    Activations Density 0.112%

    No Known Activations