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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18534
    Prev
    Next
    INDEX
    Explanations

    logo or brand

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     интим
    -0.08
     поверхность
    -0.08
     beforehand
    -0.08
     подготов
    -0.08
     तैयारी
    -0.08
     ceilings
    -0.08
     पू
    -0.08
     xuống
    -0.08
     дополн
    -0.08
     Nachdem
    -0.08
    POSITIVE LOGITS
    /logo
    0.17
    .logo
    0.16
    .brand
    0.15
     branding
    0.14
    Logo
    0.14
    _logo
    0.14
    -logo
    0.14
     Branding
    0.14
     logo
    0.14
    _brand
    0.14
    Activations Density 0.002%

    No Known Activations