© 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. 79026
    Prev
    Next
    INDEX
    Explanations

    int

    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
    comp
    -0.10
    Comp
    -0.08
     fascin
    -0.08
     Heck
    -0.07
     Comp
    -0.07
     grapp
    -0.07
    .TH
    -0.07
     Bee
    -0.07
     Hal
    -0.07
     ingresso
    -0.07
    POSITIVE LOGITS
    研
    0.09
     দেখতে
    0.09
    -cut
    0.08
     দেখা
    0.08
     lone
    0.08
     neglected
    0.08
    റണ
    0.08
     EPC
    0.08
     isle
    0.08
    -eyed
    0.08
    Activations Density 0.005%

    No Known Activations