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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29626
    Prev
    Next
    INDEX
    Explanations

    mimosas

    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
     andro
    -0.08
    isto
    -0.08
    .attribute
    -0.08
     oed
    -0.08
    稿
    -0.08
    功
    -0.08
     reg
    -0.08
     intellig
    -0.07
     язык
    -0.07
    keypress
    -0.07
    POSITIVE LOGITS
     conferences
    0.08
     RSVP
    0.08
    Conference
    0.08
     peas
    0.08
     mortar
    0.07
     preved
    0.07
     towns
    0.07
     precipitation
    0.07
     bowl
    0.07
    pea
    0.07
    Activations Density 0.019%

    No Known Activations