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. 102826
    Prev
    Next
    INDEX
    Explanations

    there

    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
     Snap
    -0.09
     BBQ
    -0.08
     ব
    -0.08
     snap
    -0.08
     BCM
    -0.07
     محور
    -0.07
    rawl
    -0.07
     trampoline
    -0.07
    763
    -0.07
    aci
    -0.07
    POSITIVE LOGITS
     않았
    0.08
     attributed
    0.08
    ома
    0.08
    _INFINITY
    0.08
    出处
    0.08
     ʻana
    0.08
    ỳ
    0.08
    来源
    0.08
     eyebrows
    0.08
     reasoning
    0.08
    Activations Density 0.003%

    No Known Activations