© 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. 47916
    Prev
    Next
    INDEX
    Explanations

    cm

    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
     gezamenlijk
    -0.09
     tendre
    -0.08
     heldur
    -0.08
     crane
    -0.08
     Heer
    -0.08
     chimp
    -0.08
     Russo
    -0.08
     robo
    -0.08
    크
    -0.08
     Russians
    -0.07
    POSITIVE LOGITS
    omány
    0.08
     bestätigen
    0.07
     überprüfen
    0.07
     convierte
    0.07
     pew
    0.07
     AGE
    0.07
    �
    0.07
     �
    0.07
    .Note
    0.06
     PEM
    0.06
    Activations Density 0.004%

    No Known Activations