© 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. 97365
    Prev
    Next
    INDEX
    Explanations

    С

    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
     considers
    -0.08
     goes
    -0.08
    ignons
    -0.08
    .elastic
    -0.08
     посп
    -0.08
     Limits
    -0.07
    anks
    -0.07
    كى
    -0.07
    -ups
    -0.07
    upart
    -0.07
    POSITIVE LOGITS
    одерж
    0.16
    одержание
    0.16
    од
    0.14
    ОД
    0.13
     Inhalts
    0.11
    ъд
    0.11
     содержания
    0.11
     sadrž
    0.11
    adrž
    0.10
     contenu
    0.10
    Activations Density 0.003%

    No Known Activations