© 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. 2509
    Prev
    Next
    INDEX
    Explanations

    его

    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
     bait
    -0.07
     IMG
    -0.07
    922
    -0.07
    cnt
    -0.07
    btc
    -0.07
     Hall
    -0.07
     ba
    -0.07
    cate
    -0.07
     Baum
    -0.07
    	b
    -0.07
    POSITIVE LOGITS
     depress
    0.08
     cess
    0.08
     markings
    0.08
     Dep
    0.07
     Penn
    0.07
     conseguido
    0.07
     Troubles
    0.07
     край
    0.07
    旅游
    0.07
    גיע
    0.07
    Activations Density 0.001%

    No Known Activations