© 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. 11-RESID-POST-AA
    11. 70000
    Prev
    Next
    INDEX
    Explanations

    Fahrenheit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Formation
    -0.08
    /vue
    -0.08
     formation
    -0.08
    -0.07
    Breadcrumb
    -0.07
     ét
    -0.07
    Token
    -0.07
    ena
    -0.07
     intestinal
    -0.07
    /tag
    -0.07
    POSITIVE LOGITS
    ahrenheit
    0.13
     ताप
    0.12
     Fahrenheit
    0.11
     temperatuur
    0.10
     температура
    0.10
     Temperatur
    0.10
     Temperaturen
    0.10
     الحرارة
    0.09
     temperatures
    0.09
     температуры
    0.09
    Activations Density 0.005%
    No Known Activations