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. 65611
    Prev
    Next
    INDEX
    Explanations

    canal

    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
     scratching
    -0.08
     מיר
    -0.08
     दर्द
    -0.08
     grind
    -0.08
     obtuvo
    -0.08
     vernieuw
    -0.08
    PX
    -0.08
     heel
    -0.08
    ,提高
    -0.08
    быз
    -0.08
    POSITIVE LOGITS
     Bottle
    0.09
     Wunsch
    0.08
     Boc
    0.07
     chemically
    0.07
     envie
    0.07
    разу
    0.07
    0.07
     stup
    0.07
     bottles
    0.07
     umur
    0.07
    Activations Density 0.001%

    No Known Activations