© 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. 11-RESID-POST-AA
    11. 24967
    Prev
    Next
    INDEX
    Explanations

    Words with affixes

    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
    LEGAL
    -0.09
    ่
    -0.08
    isd
    -0.08
     মামলা
    -0.08
     国家
    -0.07
     pomoći
    -0.07
     Cesar
    -0.07
    -0.07
    ça
    -0.07
     MISS
    -0.07
    POSITIVE LOGITS
    ?!
    0.09
     (=
    0.08
    )set
    0.08
    sic
    0.07
    /by
    0.07
    nii
    0.07
    )t
    0.07
     phenomenal
    0.07
     serre
    0.07
     galerie
    0.07
    Activations Density 0.041%
    No Known Activations