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. 111937
    Prev
    Next
    INDEX
    Explanations

    factors

    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
     Shim
    -0.10
     Yam
    -0.08
     homo
    -0.08
    jons
    -0.08
    ési
    -0.07
    to
    -0.07
     Falk
    -0.07
    Bart
    -0.07
    tle
    -0.07
     брать
    -0.07
    POSITIVE LOGITS
    因素
    0.16
     factores
    0.11
     factors
    0.10
     Faktoren
    0.10
     Factors
    0.10
     influencing
    0.10
    Factors
    0.09
     facteurs
    0.09
     fatores
    0.09
     عوامل
    0.09
    Activations Density 0.019%

    No Known Activations