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. 76365
    Prev
    Next
    INDEX
    Explanations

    protection from sun/heat

    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
     popul
    -0.08
    (cont
    -0.08
     existência
    -0.08
    ocial
    -0.07
     Phase
    -0.07
    ategoria
    -0.07
     النجاح
    -0.07
     contamin
    -0.07
    perate
    -0.07
    _mysql
    -0.07
    POSITIVE LOGITS
     sunlight
    0.10
     glare
    0.09
     prolonged
    0.08
     shafts
    0.08
     सूर्य
    0.08
     amarillo
    0.08
    紫
    0.08
     sunscreen
    0.08
     ту
    0.08
     солн
    0.08
    Activations Density 0.021%

    No Known Activations