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. 45478
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    _attributes
    -0.08
     Bytes
    -0.08
    _boolean
    -0.08
     nachvoll
    -0.08
    _bytes
    -0.07
    _tracking
    -0.07
    -0.07
     efficiency
    -0.07
     ottenere
    -0.07
    _instruction
    -0.07
    POSITIVE LOGITS
     drafted
    0.12
     draft
    0.11
    draft
    0.10
     drafting
    0.10
    Draft
    0.10
     Draft
    0.09
     shortlisted
    0.09
     deadline
    0.09
     حملة
    0.09
     drafts
    0.09
    Activations Density 0.026%

    No Known Activations