© 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. 11-RESID-POST-AA
    11. 8181
    Prev
    Next
    INDEX
    Explanations

    LAN/VLAN

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     בעבר
    -0.08
     Lisp
    -0.08
    Л
    -0.07
    _ln
    -0.07
    лын
    -0.07
    agan
    -0.07
    דה
    -0.07
    (error
    -0.07
    Glyph
    -0.07
     remplac
    -0.07
    POSITIVE LOGITS
     Helsing
    0.08
     HDMI
    0.08
     kabel
    0.08
     लाइव
    0.08
     بندی
    0.08
     Helsinki
    0.08
     Hus
    0.08
     beliau
    0.07
     hopping
    0.07
    ٽي
    0.07
    Activations Density 0.001%

    No Known Activations