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. 45092
    Prev
    Next
    INDEX
    Explanations

    slanted light

    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
     ಆರ
    -0.08
    (unsigned
    -0.08
     ئار
    -0.08
    励
    -0.08
     أر
    -0.07
    inematic
    -0.07
    'ann
    -0.07
     فوائد
    -0.07
     أعمال
    -0.07
     agitation
    -0.07
    POSITIVE LOGITS
     sideways
    0.09
     teenagers
    0.08
     diagon
    0.08
     podat
    0.07
     Subaru
    0.07
     Gear
    0.07
    ாட
    0.07
     modifies
    0.07
     malam
    0.07
     zukünft
    0.07
    Activations Density 0.006%

    No Known Activations