© 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. 23-RESID-POST-AA
    11. 50824
    Prev
    Next
    INDEX
    Explanations

    т

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    put
    -0.09
    ulls
    -0.09
     Management
    -0.08
    cis
    -0.08
    ileo
    -0.08
    shops
    -0.08
    rare
    -0.08
    elic
    -0.08
    shop
    -0.08
    .ce
    -0.07
    POSITIVE LOGITS
    ябрь
    0.17
    ября
    0.15
    ябр
    0.14
    ябре
    0.13
    եմբ
    0.12
    ूबर
    0.12
    עמבער
    0.12
    ემბერს
    0.11
    ോബ
    0.11
    ubre
    0.10
    Activations Density 0.000%

    No Known Activations