© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 26490
    Prev
    Next
    INDEX
    Explanations

    context

    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
    astery
    -0.08
    vara
    -0.07
    raiser
    -0.07
    gressive
    -0.07
    lecht
    -0.07
     parser
    -0.07
     易
    -0.07
    zada
    -0.07
    Signup
    -0.07
    정
    -0.07
    POSITIVE LOGITS
     alimentar
    0.09
     Umm
    0.08
     computers
    0.08
     आकार
    0.08
    /input
    0.08
     liter
    0.08
     psychiatr
    0.08
    FD
    0.08
     क्षमता
    0.07
     habilidade
    0.07
    Activations Density 0.002%

    No Known Activations