© 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. 11-RESID-POST-AA
    11. 79303
    Prev
    Next
    INDEX
    Explanations

    horizontal separators

    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
     Pip
    -0.08
     sluggish
    -0.08
     apparent
    -0.08
     দক্ষ
    -0.07
     efficient
    -0.07
     possess
    -0.07
     suffer
    -0.07
     correta
    -0.07
     salvation
    -0.07
     Pit
    -0.07
    POSITIVE LOGITS
    Separator
    0.15
     separator
    0.13
    Divider
    0.13
     Separator
    0.13
     Divider
    0.13
     separators
    0.13
    separator
    0.12
     divider
    0.12
    .separator
    0.12
    -divider
    0.12
    Activations Density 0.015%

    No Known Activations