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. 9063
    Prev
    Next
    INDEX
    Explanations

    right left

    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
    icka
    -0.07
     Howard
    -0.07
    _bytes
    -0.07
     cấu
    -0.07
    ри
    -0.07
     �
    -0.07
    /plugins
    -0.07
    Pron
    -0.07
    _ratio
    -0.07
    Radius
    -0.07
    POSITIVE LOGITS
     counterpart
    0.08
     formar
    0.08
    כר
    0.08
    娃
    0.08
     открыть
    0.08
     دب
    0.07
    567
    0.07
    版本
    0.07
     wers
    0.07
     ev
    0.07
    Activations Density 0.011%

    No Known Activations