© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 99264
    Prev
    Next
    INDEX
    Explanations

    Glycolysis

    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
    jež
    -0.08
    iesz
    -0.08
    /styles
    -0.08
     subscribed
    -0.08
    sker
    -0.08
    adhi
    -0.07
     subway
    -0.07
     हवा
    -0.07
    	room
    -0.07
     departed
    -0.07
    POSITIVE LOGITS
     fanno
    0.09
     byly
    0.08
     fase
    0.08
    ffe
    0.08
     nhé
    0.08
    ાંડ
    0.08
     story
    0.08
     passiert
    0.08
     vég
    0.08
     трей
    0.08
    Activations Density 0.001%

    No Known Activations