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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 102910
    Prev
    Next
    INDEX
    Explanations

    Negative numbers

    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
    Inspired
    -0.08
    @Builder
    -0.08
    DIY
    -0.07
     scu
    -0.07
     વગર
    -0.07
    Factory
    -0.07
    issionais
    -0.07
    resize
    -0.07
     pulver
    -0.07
    Wifi
    -0.07
    POSITIVE LOGITS
     negative
    0.16
     negativity
    0.14
     negatieve
    0.14
     numeric
    0.14
     Negative
    0.13
     numerical
    0.13
     negat
    0.13
    negative
    0.13
     negativos
    0.13
     negatives
    0.13
    Activations Density 0.042%

    No Known Activations