© 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. 96826
    Prev
    Next
    INDEX
    Explanations

    ител/ател

    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
    liyi
    -0.10
    ة
    -0.09
    delta
    -0.08
    reibung
    -0.08
    acijo
    -0.08
    i
    -0.08
    intha
    -0.08
    ction
    -0.08
    zi
    -0.07
    zaal
    -0.07
    POSITIVE LOGITS
    нь
    0.10
    ен
    0.10
    ియన్
    0.09
    iów
    0.08
     eastern
    0.08
    ಿಯನ್
    0.08
    Ь
    0.08
    ендә
    0.08
     tweaks
    0.08
    enya
    0.07
    Activations Density 0.003%

    No Known Activations