© 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. 652
    Prev
    Next
    INDEX
    Explanations

    Forceful impact

    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
     hinsichtlich
    -0.09
    xffff
    -0.08
     pente
    -0.08
     nikdy
    -0.08
     penetrate
    -0.08
    .jav
    -0.08
     specialise
    -0.08
    әх
    -0.07
     নম
    -0.07
    берите
    -0.07
    POSITIVE LOGITS
     clam
    0.08
     idol
    0.08
     Drog
    0.07
     ming
    0.07
     fest
    0.07
     Barn
    0.07
     tofu
    0.07
     heroic
    0.07
     Rick
    0.07
     mechanics
    0.07
    Activations Density 0.021%

    No Known Activations