Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 11591
    Prev
    Next
    INDEX
    Explanations

    Number three

    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
     ನಿಮ
    -0.07
    163
    -0.07
     colt
    -0.07
    doing
    -0.07
     Cere
    -0.07
     conocimientos
    -0.07
    themes
    -0.07
     kertaa
    -0.07
     కాగా
    -0.07
     nueve
    -0.07
    POSITIVE LOGITS
     disguised
    0.08
    IPAL
    0.08
     handshake
    0.07
     chap
    0.07
    ித்
    0.07
     Firewall
    0.07
    elaas
    0.07
    ノ
    0.07
     exam
    0.07
     sloppy
    0.07
    Activations Density 0.001%

    No Known Activations