© 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. 23-RESID-POST-AA
    11. 48767
    Prev
    Next
    INDEX
    Explanations

    Perg

    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
    zione
    -0.09
    ziens
    -0.09
    ekin
    -0.09
    zić
    -0.09
    rail
    -0.08
    merci
    -0.08
    _ke
    -0.08
     horses
    -0.08
    Boom
    -0.08
    bo
    -0.08
    POSITIVE LOGITS
    unta
    0.16
    unte
    0.15
    untas
    0.13
    untar
    0.12
    amin
    0.12
    амин
    0.11
     nam
    0.11
    unto
    0.10
    uições
    0.09
    UNT
    0.09
    Activations Density 0.001%

    No Known Activations