© 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. 48556
    Prev
    Next
    INDEX
    Explanations

    p

    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
    šče
    -0.09
     abar
    -0.08
    ્ઠ
    -0.08
     وغير
    -0.08
    .sem
    -0.08
     centaines
    -0.08
    ायण
    -0.08
     dizaines
    -0.08
    etet
    -0.08
    -0.08
    POSITIVE LOGITS
    ਿੰ
    0.09
    িল
    0.09
    ింప
    0.09
    ిల్
    0.09
    িগ
    0.09
    ిక్
    0.08
    েয়ার
    0.08
    incare
    0.08
    ర్చ
    0.08
    িকার
    0.08
    Activations Density 0.024%
    No Known Activations