© 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. 23-RESID-POST-AA
    11. 48480
    Prev
    Next
    INDEX
    Explanations

    Jun

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lep
    -0.08
     capitals
    -0.08
     hadd
    -0.08
     équ
    -0.07
     aankoop
    -0.07
     measuring
    -0.07
    wiek
    -0.07
     equities
    -0.07
     Indie
    -0.07
    B
    -0.07
    POSITIVE LOGITS
     suffering
    0.08
    ering
    0.07
     chewing
    0.07
    grim
    0.07
    imos
    0.07
    au
    0.07
    chini
    0.07
    pris
    0.07
    /an
    0.07
    _Msp
    0.07
    Activations Density 0.000%

    No Known Activations