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. 45087
    Prev
    Next
    INDEX
    Explanations

    math formulas

    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
     Rever
    -0.08
     revisions
    -0.08
     उसने
    -0.07
    (inst
    -0.07
     ou
    -0.07
     оз
    -0.07
     Orange
    -0.07
    Revision
    -0.07
    ками
    -0.07
     hebben
    -0.07
    POSITIVE LOGITS
     fracaso
    0.10
    rafo
    0.08
    anato
    0.08
    ieht
    0.08
    raulic
    0.07
    など
    0.07
    ndi
    0.07
    טח
    0.07
    osto
    0.07
    yno
    0.07
    Activations Density 0.060%

    No Known Activations