© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 24742
    Prev
    Next
    INDEX
    Explanations

    all

    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
     ähnlich
    -0.08
     bezeichnet
    -0.08
    igits
    -0.07
     kons
    -0.07
     kurzer
    -0.07
    zin
    -0.07
     können
    -0.07
     kann
    -0.07
     LIKE
    -0.07
     ermöglicht
    -0.07
    POSITIVE LOGITS
    ,但
    0.09
     küll
    0.09
    ,但是
    0.09
     acknowledging
    0.09
     considering
    0.09
     لیکن
    0.09
     nonetheless
    0.08
     draining
    0.08
    👏
    0.08
    🙏
    0.08
    Activations Density 0.161%

    No Known Activations