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. 109651
    Prev
    Next
    INDEX
    Explanations

    butterfly

    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
     Governor
    -0.08
     शासन
    -0.07
     cé
    -0.07
    	Name
    -0.07
    טן
    -0.07
     Hoc
    -0.07
    	me
    -0.07
     Approved
    -0.07
     Spread
    -0.07
     желез
    -0.07
    POSITIVE LOGITS
    Adv
    0.09
     Adv
    0.09
    idot
    0.09
    -message
    0.08
     avanzado
    0.08
    064
    0.08
     advancement
    0.08
    illant
    0.08
    алав
    0.08
    Advanced
    0.08
    Activations Density 0.000%

    No Known Activations