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. 74396
    Prev
    Next
    INDEX
    Explanations

    inference from observation

    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
     erklären
    -0.08
     explicar
    -0.08
     possuir
    -0.08
     expliquer
    -0.08
     repetir
    -0.08
     COUNT
    -0.08
     Bubble
    -0.08
     explica
    -0.08
     explaining
    -0.08
    <E
    -0.08
    POSITIVE LOGITS
     infer
    0.13
     glean
    0.12
     inferred
    0.12
     clues
    0.11
    猜
    0.11
     अनुमान
    0.11
     discern
    0.11
    Infer
    0.11
    Guess
    0.10
     cues
    0.10
    Activations Density 0.086%

    No Known Activations