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. 48850
    Prev
    Next
    INDEX
    Explanations

    (

    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
    Overs
    -0.08
    .par
    -0.07
    're
    -0.07
    asti
    -0.07
     tect
    -0.07
     noter
    -0.07
     Overs
    -0.07
     assignments
    -0.07
     regi
    -0.07
     Ret
    -0.07
    POSITIVE LOGITS
    )["
    0.09
    ยุ
    0.08
     Tul
    0.08
    最好
    0.08
     pandemia
    0.08
     Plane
    0.08
     �
    0.08
     citoy
    0.08
    yyvsp
    0.07
     sightseeing
    0.07
    Activations Density 0.049%

    No Known Activations