© 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. 102929
    Prev
    Next
    INDEX
    Explanations

    chain

    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
    ificar
    -0.11
    ifique
    -0.09
     fydd
    -0.09
    ificeerd
    -0.09
    �ი
    -0.09
    ificados
    -0.08
    ifax
    -0.08
    ifica
    -0.08
    ihaz
    -0.08
    ước
    -0.08
    POSITIVE LOGITS
     chain
    0.15
     Chain
    0.14
    Chain
    0.14
    _chain
    0.13
    chain
    0.12
    链
    0.12
    _CHAIN
    0.11
     chains
    0.11
    -chain
    0.10
    (chain
    0.10
    Activations Density 0.021%

    No Known Activations