© 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. 8038
    Prev
    Next
    INDEX
    Explanations

    water

    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
     Youtube
    -0.08
    ussy
    -0.08
    ablishment
    -0.07
    unuz
    -0.07
    unun
    -0.07
    ателям
    -0.07
    	Connection
    -0.07
    یکار
    -0.07
     কলেজ
    -0.07
    (scale
    -0.07
    POSITIVE LOGITS
     synthesized
    0.08
    에서도
    0.07
     Sinclair
    0.07
     supon
    0.07
     acceptable
    0.07
    ífico
    0.07
    .common
    0.07
    Synth
    0.07
     synthesis
    0.07
     moisture
    0.07
    Activations Density 0.009%

    No Known Activations