© 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. 103107
    Prev
    Next
    INDEX
    Explanations

    time

    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
     использование
    -0.08
    009
    -0.08
     собы
    -0.08
     %@
    -0.08
     жағ
    -0.07
    စ်
    -0.07
     사건
    -0.07
     выкары
    -0.07
     изменение
    -0.07
    	elseif
    -0.07
    POSITIVE LOGITS
     disponíveis
    0.14
     available
    0.13
     disponibles
    0.13
     disponível
    0.13
     plenty
    0.12
     tersedia
    0.12
     disponibili
    0.12
     disponible
    0.11
     enough
    0.11
     Available
    0.11
    Activations Density 0.025%

    No Known Activations