Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43693
    Prev
    Next
    INDEX
    Explanations

    Cabinet

    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
     Kis
    -0.08
     confection
    -0.08
     pup
    -0.08
     Pup
    -0.07
     Ukr
    -0.07
    Scratch
    -0.07
     Kong
    -0.07
     Dana
    -0.07
     crap
    -0.07
     Caj
    -0.07
    POSITIVE LOGITS
    室
    0.09
     под
    0.08
    iliary
    0.08
     trag
    0.08
    aghan
    0.08
    字号
    0.07
     hei
    0.07
    mates
    0.07
     Esse
    0.07
    ACA
    0.07
    Activations Density 0.009%

    No Known Activations