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. 9092
    Prev
    Next
    INDEX
    Explanations

    hunger

    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
     Знач
    -0.09
     sichern
    -0.08
    _branch
    -0.08
     Very
    -0.08
     Из
    -0.08
    Из
    -0.08
    (eq
    -0.07
    میم
    -0.07
     Zn
    -0.07
     Famous
    -0.07
    POSITIVE LOGITS
     cravings
    0.10
     physiological
    0.10
     physiology
    0.10
     cues
    0.09
     aches
    0.09
     hunger
    0.09
     hormones
    0.09
     discomfort
    0.09
     offended
    0.08
    argi
    0.08
    Activations Density 0.007%

    No Known Activations