© 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. 48166
    Prev
    Next
    INDEX
    Explanations

    c

    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
    ট
    -0.08
    ဲ့
    -0.08
    াস্ট
    -0.08
    ಾಟ್
    -0.08
     ট
    -0.08
    ীল
    -0.08
     asil
    -0.08
     depict
    -0.08
    igste
    -0.07
    ig
    -0.07
    POSITIVE LOGITS
    ap
    0.14
    	ap
    0.10
    AP
    0.09
    aps
    0.09
     ap
    0.09
    apsulation
    0.09
    apas
    0.08
    ODO
    0.08
    apan
    0.08
    od
    0.08
    Activations Density 0.013%

    No Known Activations