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. 111468
    Prev
    Next
    INDEX
    Explanations

    Scientific findings and analysis

    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
     annoying
    -0.08
     hanyar
    -0.08
     annoy
    -0.08
    https
    -0.08
     attractiveness
    -0.08
     catchy
    -0.07
     fw
    -0.07
     sonuc
    -0.07
     incó
    -0.07
     implicitly
    -0.07
    POSITIVE LOGITS
     Evidence
    0.12
     evidence
    0.12
     свидетель
    0.11
    Evidence
    0.11
     Hinweise
    0.11
    indic
    0.11
     témoign
    0.11
     evid
    0.11
     indicates
    0.10
     indicative
    0.10
    Activations Density 0.060%

    No Known Activations