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. 59609
    Prev
    Next
    INDEX
    Explanations

    turning/curves

    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
     Table
    -0.08
     Leb
    -0.08
    uyu
    -0.08
     att
    -0.07
     Glitter
    -0.07
    ем
    -0.07
    ongo
    -0.07
    ethyl
    -0.07
    ình
    -0.07
    .cell
    -0.07
    POSITIVE LOGITS
     abrupt
    0.09
    曲
    0.09
     Fairfax
    0.09
     sharply
    0.08
     abruptly
    0.08
    ACLE
    0.08
     bend
    0.08
    ाकार
    0.08
     bends
    0.08
     Junction
    0.08
    Activations Density 0.015%

    No Known Activations