© 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. 19-RESID-POST-AA
    11. 102869
    Prev
    Next
    INDEX
    Explanations

    several

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    's
    -0.08
    _,
    -0.08
    ροφο
    -0.07
    uppen
    -0.07
    ்வே
    -0.07
     varsa
    -0.07
    ’s
    -0.07
    ansen
    -0.07
    angrijk
    -0.07
    "`
    -0.07
    POSITIVE LOGITS
     several
    0.46
    Several
    0.39
     Several
    0.39
     plusieurs
    0.36
     kilku
    0.35
     někol
    0.35
    几个
    0.34
     birkaç
    0.34
     flera
    0.34
     několik
    0.34
    Activations Density 0.109%

    No Known Activations