© 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. 108813
    Prev
    Next
    INDEX
    Explanations

    directors

    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
    reten
    -0.07
    Crypto
    -0.07
     furnishing
    -0.07
     glim
    -0.07
    /artificial
    -0.07
     exhaustion
    -0.07
    -tab
    -0.07
    ithmetic
    -0.07
    Generate
    -0.07
     siph
    -0.07
    POSITIVE LOGITS
    导演
    0.19
     దర్శకత్వ
    0.17
     auteur
    0.17
     filmmaker
    0.16
     దర్శక
    0.16
     സംവിധായ
    0.16
     filmmakers
    0.15
     реж
    0.15
     감독
    0.14
     auteurs
    0.13
    Activations Density 0.085%

    No Known Activations