© 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 EvalsExportsAPI 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. 49700
    Prev
    Next
    INDEX
    Explanations

    reach

    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
     upright
    -0.08
     खुश
    -0.08
     propostas
    -0.07
    -theme
    -0.07
    ليات
    -0.07
    ля
    -0.07
     prosec
    -0.07
     satisfacción
    -0.07
     Stylish
    -0.07
     JSX
    -0.07
    POSITIVE LOGITS
     reach
    0.27
     Reach
    0.24
    Reach
    0.24
     পৌঁ
    0.22
     reaches
    0.22
     reaching
    0.21
    reach
    0.21
     alcance
    0.20
     પહોંચ
    0.20
     bereik
    0.20
    Activations Density 0.081%

    No Known Activations