© 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. 96800
    Prev
    Next
    INDEX
    Explanations

    iy

    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
    ാണ്
    -0.24
    ಾಗ
    -0.23
    ിലെ
    -0.21
    ിൽ
    -0.20
    ായ
    -0.20
    ான
    -0.19
    ாக
    -0.19
    ില്
    -0.17
    ின்
    -0.17
    ில்
    -0.17
    POSITIVE LOGITS
    йтесь
    0.09
    ોગ્ય
    0.09
    тым
    0.09
    ുടെയും
    0.09
    न्त्रण
    0.08
    й
    0.08
    alselt
    0.08
    луу
    0.08
    лык
    0.08
    ләр
    0.08
    Activations Density 0.042%

    No Known Activations