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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 119271
    Prev
    Next
    INDEX
    Explanations

    .ai

    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
     duly
    -0.09
     rune
    -0.08
    NASA
    -0.07
     refriger
    -0.07
     Nm
    -0.07
    Fragments
    -0.07
     Myth
    -0.07
    രിപ്പ
    -0.07
    리아
    -0.07
     â
    -0.07
    POSITIVE LOGITS
    .second
    0.11
    .blue
    0.09
     bolet
    0.09
    _boot
    0.09
    second
    0.09
    .speed
    0.08
    .FL
    0.08
    .sex
    0.08
    .fl
    0.08
    .sign
    0.08
    Activations Density 0.000%

    No Known Activations