Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 77781
    Prev
    Next
    INDEX
    Explanations

    Negation/difference

    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
    antil
    -0.08
    余额
    -0.08
     daftar
    -0.08
     irrespons
    -0.08
     greed
    -0.08
     precipit
    -0.07
    자를
    -0.07
    acher
    -0.07
     preceded
    -0.07
    /File
    -0.07
    POSITIVE LOGITS
     similarities
    0.23
     resemblance
    0.20
     similarity
    0.19
    Similarity
    0.18
     совп
    0.18
    _similarity
    0.17
     сход
    0.14
     overlap
    0.14
     likeness
    0.13
     overlaps
    0.13
    Activations Density 0.111%

    No Known Activations