© 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. 75587
    Prev
    Next
    INDEX
    Explanations

    Formatting characters

    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
     rutina
    -0.09
     tweeted
    -0.08
    一分钟
    -0.08
     inspire
    -0.08
     carrera
    -0.08
     esfuerzo
    -0.08
     rotina
    -0.07
     Politics
    -0.07
    ଛ
    -0.07
     absurdo
    -0.07
    POSITIVE LOGITS
     parties
    0.12
     LLC
    0.12
    Recipient
    0.12
    双方
    0.12
     recipients
    0.11
     recipient
    0.11
     beneficiaries
    0.11
     ООО
    0.11
     Parteien
    0.11
     defendants
    0.10
    Activations Density 0.016%

    No Known Activations