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. 90460
    Prev
    Next
    INDEX
    Explanations

    36

    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
    orius
    -0.08
     എണ്ണ
    -0.08
     आल
    -0.07
     para
    -0.07
     stalking
    -0.07
    ource
    -0.07
     Secretary
    -0.07
     maxima
    -0.07
    流水
    -0.07
    Chef
    -0.07
    POSITIVE LOGITS
     영향을
    0.08
     влияние
    0.08
     보험
    0.08
     eerlijk
    0.08
    irt
    0.08
     снижение
    0.08
    هنية
    0.08
     привед
    0.07
    (Thread
    0.07
    velopment
    0.07
    Activations Density 0.001%

    No Known Activations