© 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. 3-RESID-POST-AA
    11. 12870
    Prev
    Next
    INDEX
    Explanations

    -F

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -0.09
    だから
    -0.08
     tx
    -0.08
     Ode
    -0.08
    _SMALL
    -0.08
    ādi
    -0.08
     التنظيم
    -0.07
    ांश
    -0.07
    (dx
    -0.07
    ੰਤ
    -0.07
    POSITIVE LOGITS
     designated
    0.09
    *-
    0.08
    /-
    0.08
     Vac
    0.08
    nan
    0.08
    0.08
    OF
    0.08
     
    0.07
    ition
    0.07
     cust
    0.07
    Activations Density 0.127%
    No Known Activations