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. 15-RESID-POST-AA
    6. 19558
    Prev
    Next
    INDEX
    Explanations

    Factors and primes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     temperatura
    -0.08
    嘴
    -0.08
     sfeer
    -0.08
    /customer
    -0.08
     gesture
    -0.08
     suicidal
    -0.08
     captions
    -0.07
     oot
    -0.07
    .JOption
    -0.07
    apa
    -0.07
    POSITIVE LOGITS
     facteurs
    0.13
     factors
    0.12
    Factors
    0.12
     factores
    0.12
     divis
    0.11
     Faktoren
    0.11
     fatores
    0.11
     primes
    0.11
    Factor
    0.11
     Factors
    0.11
    Activations Density 0.046%

    No Known Activations