© 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. 19090
    Prev
    Next
    INDEX
    Explanations

    legend

    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
     Such
    -0.08
     երբ
    -0.08
     એવો
    -0.08
     જેમ
    -0.08
    _COMMENT
    -0.08
    Such
    -0.08
    JSImport
    -0.08
    征
    -0.08
     kommentar
    -0.08
    أكد
    -0.08
    POSITIVE LOGITS
     positioned
    0.11
    .position
    0.11
    .location
    0.11
     위치
    0.11
    -placement
    0.11
    -location
    0.10
    -position
    0.10
    .show
    0.10
    的位置
    0.10
    position
    0.10
    Activations Density 0.001%

    No Known Activations