© 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. 12850
    Prev
    Next
    INDEX
    Explanations

    forward slash

    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
    cot
    -0.08
     बे
    -0.08
    افية
    -0.08
     TEX
    -0.07
     Libre
    -0.07
     Golf
    -0.07
     neck
    -0.07
    .Space
    -0.07
     Realty
    -0.07
     Palais
    -0.07
    POSITIVE LOGITS
     আব
    0.07
     csrf
    0.07
    任
    0.07
    geg
    0.07
    便
    0.07
     任
    0.07
    ponder
    0.07
    Ps
    0.07
    pragma
    0.07
    йте
    0.06
    Activations Density 0.001%

    No Known Activations