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. 55908
    Prev
    Next
    INDEX
    Explanations

    sentences and grammar

    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
    Pins
    -0.09
     patch
    -0.08
    Flo
    -0.08
    Diff
    -0.08
    (Float
    -0.08
     pins
    -0.08
     dipercaya
    -0.08
    Td
    -0.08
     archives
    -0.07
     precious
    -0.07
    POSITIVE LOGITS
     sentences
    0.22
    _sentence
    0.20
    句
    0.20
     sentence
    0.19
     Sentence
    0.18
    sentence
    0.18
    Sentence
    0.18
     বাক
    0.16
     frases
    0.15
    一句
    0.14
    Activations Density 0.068%

    No Known Activations