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. 78594
    Prev
    Next
    INDEX
    Explanations

    2

    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
     pillars
    -0.08
    pilot
    -0.08
    _br
    -0.08
    mem
    -0.07
    а
    -0.07
    etic
    -0.07
    -0.07
     stacking
    -0.07
    它
    -0.07
    athing
    -0.07
    POSITIVE LOGITS
    -kit
    0.08
     Toolkit
    0.08
     reportage
    0.08
     Dés
    0.08
    (Message
    0.07
     Kass
    0.07
    /sdk
    0.07
     календар
    0.07
    먹
    0.07
    Kit
    0.07
    Activations Density 0.003%

    No Known Activations