© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 79019
    Prev
    Next
    INDEX
    Explanations

    each

    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
     upravo
    -0.08
    HR
    -0.08
    ′
    -0.08
     хоч
    -0.08
     га
    -0.08
    hr
    -0.08
     právě
    -0.07
     właśnie
    -0.07
    'avez
    -0.07
     distinguishing
    -0.07
    POSITIVE LOGITS
     getter
    0.08
     individually
    0.08
     Erin
    0.08
    summer
    0.08
     correspond
    0.07
    iza
    0.07
    igita
    0.07
     erv
    0.07
     fleste
    0.07
     flesta
    0.07
    Activations Density 0.050%

    No Known Activations