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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RESID-POST-AA
    11. 69229
    Prev
    Next
    INDEX
    Explanations

    above below

    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
     doi
    -0.09
     Prob
    -0.08
     لوب
    -0.08
    Congratulations
    -0.08
    _probs
    -0.08
    א
    -0.08
     ๆ
    -0.08
    рох
    -0.08
    _prob
    -0.07
    стоящ
    -0.07
    POSITIVE LOGITS
     లేదు
    0.08
    vang
    0.07
    akia
    0.07
     banna
    0.07
     affirmative
    0.07
    Direction
    0.07
     καθώς
    0.07
     दिशा
    0.07
    iann
    0.07
     없습니다
    0.07
    Activations Density 0.004%

    No Known Activations