© 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. 47321
    Prev
    Next
    INDEX
    Explanations

    array of floats in code

    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
     susc
    -0.09
     citation
    -0.08
     sat
    -0.08
    anthem
    -0.07
     flamb
    -0.07
     lever
    -0.07
     consult
    -0.07
    とう
    -0.07
    _spell
    -0.07
     lieutenant
    -0.07
    POSITIVE LOGITS
    Pixels
    0.09
     reshape
    0.09
     organización
    0.09
     Doub
    0.08
     Px
    0.08
     poured
    0.08
    大量
    0.08
    eef
    0.08
    _ARRAY
    0.08
     doubles
    0.08
    Activations Density 0.007%

    No Known Activations