© 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. 102629
    Prev
    Next
    INDEX
    Explanations

    has

    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
    _色
    -0.11
     მქონ
    -0.11
     Have
    -0.10
     האָ
    -0.10
    _HAVE
    -0.10
     tenham
    -0.10
    _RGCTX
    -0.10
     ყოფილ
    -0.10
     tenha
    -0.10
    ’ve
    -0.10
    POSITIVE LOGITS
     provided
    0.15
     specified
    0.15
    提供
    0.15
     given
    0.14
     providing
    0.14
     proporcionar
    0.14
     fourni
    0.13
     предостав
    0.13
     написал
    0.13
     напис
    0.13
    Activations Density 0.005%

    No Known Activations