© 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. 75476
    Prev
    Next
    INDEX
    Explanations

    Formal/philosophical texts

    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
     camper
    -0.10
     swag
    -0.09
     marquee
    -0.08
     breakout
    -0.08
     snag
    -0.08
     laptop
    -0.08
     sticker
    -0.08
     ransomware
    -0.08
     raffle
    -0.08
    -testid
    -0.08
    POSITIVE LOGITS
     Nietzsche
    0.14
     divine
    0.12
     moral
    0.12
    �
    0.11
     فلس
    0.11
    哲
    0.11
     morality
    0.10
     philosophical
    0.10
     philosoph
    0.10
     Freud
    0.10
    Activations Density 0.077%

    No Known Activations