© 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. 102771
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
     bisschen
    -0.09
     spesso
    -0.09
     coração
    -0.08
     vedno
    -0.08
     ведь
    -0.08
     corazón
    -0.08
     قلب
    -0.08
     poquito
    -0.08
     overarching
    -0.08
     :).
    -0.08
    POSITIVE LOGITS
     lautet
    0.16
    如下
    0.14
     reads
    0.13
     yields
    0.12
     şöyle
    0.11
     Berikut
    0.11
     выглядит
    0.11
     以下
    0.10
     ->↵
    0.10
    以下
    0.10
    Activations Density 0.032%

    No Known Activations