© 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. 6066
    Prev
    Next
    INDEX
    Explanations

    Chinese characters

    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
    ઓ
    -0.09
    ਓ
    -0.08
    ओ
    -0.08
     gekomen
    -0.08
    ipped
    -0.08
    ueling
    -0.07
    pk
    -0.07
     Мә
    -0.07
     genuinely
    -0.07
    šo
    -0.07
    POSITIVE LOGITS
    anat
    0.10
    ants
    0.10
    ্যান
    0.10
    anship
    0.09
    anset
    0.09
    enziale
    0.09
     sistema
    0.08
    an
    0.08
    ann
    0.08
    ive
    0.08
    Activations Density 0.004%

    No Known Activations