Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 60342
    Prev
    Next
    INDEX
    Explanations

    ventilation and air

    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
     алгорит
    -0.09
     Erectile
    -0.08
     eti
    -0.08
    adha
    -0.08
     Whoever
    -0.07
     yder
    -0.07
    .rule
    -0.07
    '}}
    -0.07
     Pdf
    -0.07
     અસર
    -0.07
    POSITIVE LOGITS
     contrast
    0.08
    vum
    0.08
     ingress
    0.08
     offices
    0.08
    مص
    0.07
    -ra
    0.07
    tempo
    0.07
     Front
    0.07
     counterfeit
    0.07
     inlet
    0.07
    Activations Density 0.007%

    No Known Activations