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. 586
    Prev
    Next
    INDEX
    Explanations

    equals sign

    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
    einander
    -0.08
     hinweg
    -0.07
    abu
    -0.07
     endorse
    -0.07
    ially
    -0.07
     endorsed
    -0.07
    �
    -0.07
     verlassen
    -0.07
     endorsement
    -0.07
                          
    -0.07
    POSITIVE LOGITS
     généralement
    0.08
     Alc
    0.08
     ayuda
    0.08
     площ
    0.07
     Buena
    0.07
    0.07
     Crédit
    0.07
     një
    0.07
     clave
    0.07
     grap
    0.07
    Activations Density 0.111%

    No Known Activations