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. 65742
    Prev
    Next
    INDEX
    Explanations

    Questioning problem details

    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
    —or
    -0.08
    حق
    -0.07
     emerg
    -0.07
     また
    -0.07
    <Key
    -0.07
     cancer
    -0.07
     outright
    -0.07
     abraz
    -0.07
     كنت
    -0.07
     auftreten
    -0.07
    POSITIVE LOGITS
    unused
    0.13
    _unused
    0.11
     irrelevant
    0.11
    Unused
    0.11
     unused
    0.10
    hint
    0.10
     hint
    0.10
     hints
    0.10
     inutile
    0.09
     clues
    0.09
    Activations Density 0.082%

    No Known Activations