© 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. 63660
    Prev
    Next
    INDEX
    Explanations

    image generation prompts

    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
    782
    -0.07
    资金
    -0.07
     fonds
    -0.07
    abeh
    -0.07
    adero
    -0.07
     xo
    -0.07
     alternative
    -0.07
     board
    -0.07
     boards
    -0.07
    .awt
    -0.07
    POSITIVE LOGITS
    (theme
    0.08
     ifad
    0.08
     cliché
    0.08
    �
    0.07
    quotes
    0.07
    shi
    0.07
     wow
    0.07
     whisky
    0.07
    krivelse
    0.07
    iniz
    0.07
    Activations Density 0.021%

    No Known Activations