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. 44941
    Prev
    Next
    INDEX
    Explanations

    traffic

    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
     സാഹ
    -0.08
    DIG
    -0.08
    	write
    -0.07
     باس
    -0.07
     llevado
    -0.07
     métallique
    -0.07
     Alles
    -0.07
     masquer
    -0.07
    Steel
    -0.07
     Panic
    -0.07
    POSITIVE LOGITS
    inds
    0.09
     gifted
    0.09
     provenientes
    0.09
     확보
    0.08
     followers
    0.08
     erhöhen
    0.08
    /antlr
    0.08
     capacity
    0.08
    .capacity
    0.08
     Grecia
    0.08
    Activations Density 0.005%

    No Known Activations