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. 120170
    Prev
    Next
    INDEX
    Explanations

    Still

    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
    ORD
    -0.08
     Buying
    -0.08
     anschauen
    -0.08
    ]()
    -0.08
     fyrst
    -0.07
     freue
    -0.07
    	extern
    -0.07
     доктор
    -0.07
    (CON
    -0.07
    UNDS
    -0.07
    POSITIVE LOGITS
     waist
    0.08
     wi
    0.08
     SMB
    0.07
    alne
    0.07
    ipy
    0.07
     picnic
    0.07
     nud
    0.07
     expense
    0.07
     salário
    0.07
     deduction
    0.07
    Activations Density 0.001%

    No Known Activations