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. 3-RESID-POST-AA
    6. 2117
    Prev
    Next
    INDEX
    Explanations

    **,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Maz
    -0.09
    aliśmy
    -0.08
    മി
    -0.08
     farmer
    -0.08
     Punjab
    -0.08
     finger
    -0.07
    annis
    -0.07
    ersi
    -0.07
    -либо
    -0.07
     Mata
    -0.07
    POSITIVE LOGITS
     lij
    0.08
    �
    0.08
     gnc
    0.07
     apar
    0.07
     targ
    0.07
     cose
    0.07
     Coul
    0.07
     tle
    0.07
    
    0.07
     tack
    0.07
    Activations Density 0.000%

    No Known Activations