© 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. 2593
    Prev
    Next
    INDEX
    Explanations

    ={

    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
    760
    -0.07
     elevation
    -0.07
    ਿੱਚ
    -0.07
    -0.07
     faction
    -0.07
    ideo
    -0.07
     sr
    -0.07
     mats
    -0.07
     straw
    -0.07
    _CHANGE
    -0.07
    POSITIVE LOGITS
     Detailed
    0.08
    Implicit
    0.08
     implicitly
    0.08
     Inspector
    0.08
    ancin
    0.07
    سون
    0.07
    ناع
    0.07
     Wandel
    0.07
     underv
    0.07
     exemplar
    0.07
    Activations Density 0.000%

    No Known Activations