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. 55840
    Prev
    Next
    INDEX
    Explanations

    AdTech and Stranger Things

    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
    nan
    -0.08
     gluten
    -0.08
     Berat
    -0.07
    திர
    -0.07
    pads
    -0.07
    pad
    -0.07
    beratung
    -0.07
    rach
    -0.07
     retos
    -0.07
    trip
    -0.07
    POSITIVE LOGITS
     compensation
    0.08
    剧情
    0.08
    -ay
    0.08
     births
    0.08
     cerv
    0.08
     Amp
    0.08
     МВД
    0.07
     ঘটনা
    0.07
     episódio
    0.07
     Building
    0.07
    Activations Density 0.020%

    No Known Activations