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. 119908
    Prev
    Next
    INDEX
    Explanations

    permafrost and greenhouse gases

    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
    Շ
    -0.08
     שלך
    -0.08
     branding
    -0.08
     styling
    -0.08
     शैली
    -0.08
    יטה
    -0.07
    .us
    -0.07
     løs
    -0.07
    	children
    -0.07
    _TAB
    -0.07
    POSITIVE LOGITS
     untreated
    0.09
     kai
    0.08
     greenhouse
    0.08
     moist
    0.08
    holt
    0.08
    -oh
    0.07
     germ
    0.07
    Expiration
    0.07
     untranslated
    0.07
     unopened
    0.07
    Activations Density 0.006%

    No Known Activations