Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 102920
    Prev
    Next
    INDEX
    Explanations

    dv

    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
     taws
    -0.08
     अके
    -0.08
    lju
    -0.08
     mindset
    -0.08
     crystal
    -0.08
     vòng
    -0.08
    .Num
    -0.08
     individuality
    -0.08
     পাচ
    -0.07
    loop
    -0.07
    POSITIVE LOGITS
     Händ
    0.08
     sludge
    0.08
     stimuli
    0.08
     జరిగిన
    0.08
     festive
    0.08
     நடந்த
    0.08
    tram
    0.08
     Há
    0.08
    [].
    0.08
     Karaoke
    0.08
    Activations Density 0.001%

    No Known Activations