© 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. 23-RESID-POST-AA
    11. 6017
    Prev
    Next
    INDEX
    Explanations

    say "NS" or "DB"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ben
    -0.08
     ange
    -0.08
     subsequent
    -0.08
    ทดลอง
    -0.08
     сот
    -0.07
     manifold
    -0.07
    ರ್ಜ
    -0.07
     eth
    -0.07
     hå
    -0.07
     hope
    -0.07
    POSITIVE LOGITS
    ns
    0.15
    NS
    0.14
    BIO
    0.10
     ns
    0.10
    	ns
    0.09
    	NS
    0.09
     NS
    0.09
    AY
    0.08
    (ns
    0.08
    Graph
    0.08
    Activations Density 0.001%

    No Known Activations