Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 112045
    Prev
    Next
    INDEX
    Explanations

    Glucose/sugar

    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
     Feet
    -0.10
    Foot
    -0.10
     Foot
    -0.09
     foot
    -0.09
    foot
    -0.08
     feet
    -0.08
    	Draw
    -0.08
     mortgages
    -0.08
     Claim
    -0.08
     manager
    -0.08
    POSITIVE LOGITS
    .gamma
    0.08
    _vals
    0.08
    pro
    0.08
    -cloud
    0.08
    ninger
    0.07
    _iters
    0.07
    _uint
    0.07
    prote
    0.07
     consequent
    0.07
    _ulong
    0.07
    Activations Density 0.004%

    No Known Activations