© 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. 26622
    Prev
    Next
    INDEX
    Explanations

    end

    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
    tributions
    -0.07
     consequently
    -0.07
     stuff
    -0.07
    resp
    -0.07
     ശേഷം
    -0.07
    hrases
    -0.07
     Raising
    -0.07
     suffice
    -0.07
     ها
    -0.07
     raising
    -0.07
    POSITIVE LOGITS
     شاء
    0.08
    judice
    0.08
     vela
    0.08
     asti
    0.08
    。【
    0.08
    缘
    0.08
     danda
    0.07
     دوا
    0.07
    thair
    0.07
     möj
    0.07
    Activations Density 0.032%

    No Known Activations