© 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. 18557
    Prev
    Next
    INDEX
    Explanations

    be

    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
    増
    -0.08
    _<
    -0.08
     strengthened
    -0.08
     escalating
    -0.08
    /<
    -0.08
     surge
    -0.08
    增加
    -0.08
     surged
    -0.08
     необхід
    -0.08
    _ON
    -0.07
    POSITIVE LOGITS
     mindestens
    0.12
     minstens
    0.12
    至少
    0.11
     zumindest
    0.11
     לפחות
    0.11
     almeno
    0.11
     wenigstens
    0.10
     vähemalt
    0.10
     strictly
    0.10
     at
    0.10
    Activations Density 0.009%

    No Known Activations