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. 65158
    Prev
    Next
    INDEX
    Explanations

    possible or impossible

    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
    indic
    -0.08
     deserving
    -0.08
     ed
    -0.07
     indicative
    -0.07
    /meta
    -0.07
    -0.07
     outlining
    -0.07
     roasted
    -0.07
     suggest
    -0.07
    Ro
    -0.07
    POSITIVE LOGITS
    ,因为
    0.12
     unless
    0.11
     tenzij
    0.10
     ilegal
    0.09
     çünkü
    0.09
     لأنها
    0.09
     aufgrund
    0.08
     necesariamente
    0.08
     पिता
    0.08
     क्योंकि
    0.08
    Activations Density 0.057%

    No Known Activations