© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 8204
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     CRT
    -0.08
     हर
    -0.08
    ibrator
    -0.08
     तयार
    -0.08
    ательной
    -0.07
     Villar
    -0.07
     Wür
    -0.07
    ए
    -0.07
    ऑ
    -0.07
     cork
    -0.07
    POSITIVE LOGITS
     insult
    0.08
     vahel
    0.08
     વચ્ચે
    0.07
    dienst
    0.07
    inv
    0.07
     tenho
    0.07
     distorted
    0.07
     parade
    0.07
    indows
    0.07
    063
    0.07
    Activations Density 0.064%

    No Known Activations