© 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. 96827
    Prev
    Next
    INDEX
    Explanations

    say "units" or "ones"

    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
     Frühstück
    -0.08
    μβρίου
    -0.08
    Warum
    -0.08
    重大
    -0.08
    ышлен
    -0.08
    illante
    -0.08
    Почему
    -0.08
    แจก
    -0.07
    -0.07
    -major
    -0.07
    POSITIVE LOGITS
     units
    0.36
    units
    0.33
     unités
    0.32
     Units
    0.32
    _units
    0.32
     unidades
    0.31
     ones
    0.31
    Units
    0.30
    .units
    0.29
     unit
    0.28
    Activations Density 0.069%
    No Known Activations