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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 79128
    Prev
    Next
    INDEX
    Explanations

    geometry, tangents to circles

    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
    ورد
    -0.08
    _button
    -0.08
    _banner
    -0.08
    Banner
    -0.08
    ijų
    -0.07
    ấm
    -0.07
    umat
    -0.07
    _submit
    -0.07
    hail
    -0.07
    finally
    -0.07
    POSITIVE LOGITS
     perpendicular
    0.09
     запрещ
    0.08
     tangent
    0.08
    .Statement
    0.08
     સી
    0.08
    eser
    0.07
     सीधे
    0.07
     �
    0.07
    plt
    0.07
    cdr
    0.07
    Activations Density 0.018%

    No Known Activations