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. 43113
    Prev
    Next
    INDEX
    Explanations

    best

    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
     energized
    -0.08
    required
    -0.08
     requisite
    -0.08
     Eligible
    -0.08
     seemingly
    -0.08
     eligible
    -0.08
    needed
    -0.08
    quired
    -0.08
    _needed
    -0.07
     Used
    -0.07
    POSITIVE LOGITS
     hybride
    0.08
     investeren
    0.08
    Clamp
    0.08
     sve
    0.08
     Microgaming
    0.08
     decentral
    0.08
    Rather
    0.08
     kakhulu
    0.07
     Interview
    0.07
     Linie
    0.07
    Activations Density 0.021%

    No Known Activations