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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 47527
    Prev
    Next
    INDEX
    Explanations

    ans

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    'att
    -0.09
     August
    -0.09
    "user
    -0.09
    August
    -0.09
    'user
    -0.08
    'id
    -0.08
     echar
    -0.08
     أنت
    -0.08
    'è
    -0.08
     Aug
    -0.08
    POSITIVE LOGITS
     ans
    0.12
    ans
    0.11
    _ans
    0.10
    Ans
    0.10
     answers
    0.10
    (ans
    0.10
    _answers
    0.09
    .answers
    0.08
     answer
    0.08
    	ans
    0.08
    Activations Density 0.001%

    No Known Activations