© 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. 7-RESID-POST-AA
    11. 1283
    Prev
    Next
    INDEX
    Explanations

    Addition symbol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Key
    -0.08
     Wider
    -0.08
     Contemporary
    -0.07
    _impl
    -0.07
    Joseph
    -0.07
     साध
    -0.07
     Joseph
    -0.07
     solved
    -0.07
    solve
    -0.07
    Î
    -0.07
    POSITIVE LOGITS
    نون
    0.09
    美女
    0.09
     Cic
    0.08
    antlr
    0.08
     andro
    0.08
    咪
    0.08
    Npc
    0.07
    Tut
    0.07
     Tcl
    0.07
     bettor
    0.07
    Activations Density 0.010%

    No Known Activations