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. 534
    Prev
    Next
    INDEX
    Explanations

    meditation sitting positions

    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
     underwriting
    -0.08
    曝光
    -0.08
    _SCOPE
    -0.08
    病毒
    -0.08
                                                                       
    -0.08
    _scope
    -0.07
     scope
    -0.07
     overshadow
    -0.07
     συνα
    -0.07
     контакт
    -0.07
    POSITIVE LOGITS
     praying
    0.10
     बैठे
    0.09
    薦
    0.08
     Radical
    0.08
     sitzen
    0.08
     Clip
    0.08
     juu
    0.07
     hugged
    0.07
     comfortably
    0.07
     Suitable
    0.07
    Activations Density 0.007%

    No Known Activations